Analysis of clustered microcalcifications by using a single numeric classifier extracted from mammographic digital images

Near-infrared fluorescence imaging of microcalcification in an animal model of breast cancer

RATIONALE AND OBJECTIVES

At present, there is no animal model of breast cancer that forms reproducible microcalcification. The aim of this study was to develop a straightforward, reproducible model system that could be used to develop multimodality contrast agents for the identification of breast cancer microcalcification.

METHODS

The R3230 mammary adenocarcinoma cell line was implanted in the mammary fat pad of female Fischer 344 rats (two rats with two implanted tumors and two rats with a single implanted tumor). After growth to 1-2 cm in diameter, tumors were implanted with 100 microm hydroxyapatite crystals (positive control) or calcium oxalate crystals (negative control). Twenty-four hours after crystal implantation, rats were injected intravenously with a previously described near-infrared fluorescent bisphosphonate derivative known as Pam78, and the tumors were imaged using a reflectance optical imaging system.

RESULTS

Tumors implanted with hydroxyapatite displayed bright, focal, near-infrared fluorescence in the area of crystal implantation. Control tumors, grown in the same animal and implanted with calcium oxalate, did not display any near-infrared fluorescence, even along the needle track used for crystal implantation.

CONCLUSIONS

A simple and rapid animal model of focal calcification in breast cancer tumors has been developed and validated. The model used Pam78, a near-infrared fluorescent contrast agent specific for hydroxyapatite. The potential usefulness of the model for developing similar contrast agents for magnetic resonance and other imaging modalities is discussed.

Automated storage and retrieval of thin-section CT images to assist diagnosis: system description and preliminary assessment

A software system and database for computer-aided diagnosis with thin-section computed tomographic (CT) images of the chest was designed and implemented. When presented with an unknown query image, the system uses pattern recognition to retrieve visually similar images with known diagnoses from the database. A preliminary validation trial was conducted with 11 volunteers who were asked to select the best diagnosis for a series of test images, with and without software assistance. The percentage of correct answers increased from 29% to 62% with computer assistance. This finding suggests that this system may be useful for computer-assisted diagnosis.

Can the size of microcalcifications predict malignancy of clusters at mammography?

RATIONALE AND OBJECTIVES

The purpose of this study was to determine whether the size of mammographically detected microcalcifications is predictive of malignancy.

MATERIALS AND METHODS

Two hundred sixty mammograms showing clustered microcalcifications with proven diagnoses (160 malignant, 100 benign) were respectively reviewed by experienced mammographers. Lesions that were obviously benign in appearance were excluded from the study. A computer-aided diagnosis system digitized the lesions at 600 dpi, and the microcalcifications on the digital image were interactively defined by mammographers. Subsequently, three quantitative features that reflected the size of the microcalcifications-length, area, and brightness-were automatically extracted by the system. For each feature, the standard average of values obtained for individual calcifications within the cluster and the average with emphasis on extreme values (E) obtained in a single cluster were analyzed and matched with pathologic results.

RESULTS

In the malignant group of cases, the mean values of the standard average length and area were significantly higher (P < .0001) than the mean values in the benign group. Distribution analysis demonstrated that an average length of more than 0.41 mm was associated with malignant lesions 77% of the time, while an average length of less than 0.41 mm was associated with benign lesions 71% of the time. The mean of the average length (E) and area (E) of microcalcifications within the cluster demonstrated an even higher discriminative power when compared with the standard average length and area. The average brightness, on the other hand, showed only a low discriminative power.

CONCLUSION

Digital computerized analysis of mammographically detected calcifications demonstrated that the average length and area of the calcifications in benign clusters were significantly smaller than those in malignant clusters.

Use of artificial neural networks (computer analysis) in the diagnosis of microcalcifications on mammography

INTRODUCTION/OBJECTIVE

The purpose of this study was to evaluate a computer based method for differentiating malignant from benign clustered microcalcifications, comparing it with the performance of three physicians.

METHODS AND MATERIAL

Materials for the study are 240 suspicious microcalcifications on mammograms from 220 female patients who underwent breast biopsy, following hook wire localization under mammographic guidance. The histologic findings were malignant in 108 cases (45%) and benign in 132 cases (55%). Those clusters were analyzed by a computer program and eight features of the calcifications (density, number, area, brightness, diameter average, distance average, proximity average, perimeter compacity average) were quantitatively estimated by a specific artificial neural network. Human input was limited to initial identification of the calcifications. Three physicians-observers were also evaluated for the malignant or benign nature of the clustered microcalcifications.

RESULTS

The performance of the artificial network was evaluated by receiver operating characteristics (ROC) curves. ROC curves were also generated for the performance of each observer and for the three observers as a group. The ROC curves for the computer and for the physicians were compared and the results are:area under the curve (AUC) value for computer is 0.937, for physician-1 is 0.746, for physician-2 is 0.785, for physician-3 is 0.835 and for physicians as a group is 0.810. The results of the Student's t-test for paired data showed statistically significant difference between the artificial neural network and the physicians' performance, independently and as a group.

DISCUSSION AND CONCLUSION

Our study showed that computer analysis achieves statistically significantly better performance than that of physicians in the classification of malignant and benign calcifications. This method, after further evaluation and improvement, may help radiologists and breast surgeons in better predictive estimation of suspicious clustered microcalcifications and reduce the number of biopsies for non-palpable benign lesions.

Evaluation of linear and nonlinear tomosynthetic reconstruction methods in digital mammography

RATIONALE AND OBJECTIVES

The purpose of this study was to comparatively evaluate digital planar mammography and both linear and nonlinear tomosynthetic reconstruction methods.

MATERIALS AND METHODS

A "disk" (ie, target) identification study was conducted to compare planar and reconstruction methods. Projective data using a composite phantom with circular disks were acquired in both planar and tomographic modes by using a full-field, digital mammographic system. Two-dimensional projections were reconstructed with both linear (ie, backprojection) and nonlinear (ie, maximization and minimization) tuned-aperture computed tomographic (TACT) methods to produce three-dimensional data sets. Four board-certified radiologists and one 4th-year radiology resident participated as observers. All images were compared by these observers in terms of the number of disks identified.

RESULTS

Significant differences (P < .05, Bonferroni adjusted) were observed between all reconstruction and planar methods. No significant difference, however, was observed between the planar methods, and only a marginally significant difference (P < .054, Bonferroni adjusted) was observed between TACT-backprojection and TACT-minimization.

CONCLUSION

A combination of linear and nonlinear reconstruction schemes may have potential implications in terms of enhancing image visualization to provide radiologists with valuable diagnostic information.

Breast imaging using an amorphous silicon-based full-field digital mammographic system: stability of a clinical prototype

An amorphous silicon-based full-breast imager for digital mammography was evaluated for detector stability over a period of 1 year. This imager uses a structured CsI:TI scintillator coupled to an amorphous silicon layer with a 100-micron pixel pitch and read out by special purpose electronics. The stability of the system was characterized using the following quantifiable metrics: conversion factor (mean number of electrons generated per incident x-ray), presampling modulation transfer function (MTF), detector linearity and sensitivity, detector signal-to-noise ratio (SNR), and American College of Radiology (ACR) accreditation phantom scores. Qualitative metrics such as flat field uniformity, geometric distortion, and Society of Motion Picture and Television Engineers (SMPTE) test pattern image quality were also used to study the stability of the system. Observations made over this 1-year period indicated that the maximum variation from the average of the measurements were less than 0.5% for conversion factor, 3% for presampling MTF over all spatial frequencies, 5% for signal response, linearity and sensitivity, 12% for SNR over seven locations for all 3 target-filter combinations, and 0% for ACR accreditation phantom scores. ACR mammographic accreditation phantom images indicated the ability to resolve 5 fibers, 4 speck groups, and 5 masses at a mean glandular dose of 1.23 mGy. The SMPTE pattern image quality test for the display monitors used for image viewing indicated ability to discern all contrast steps and ability to distinguish line-pair images at the center and corners of the image. No bleeding effects were observed in the image. Flat field uniformity for all 3 target-filter combinations displayed no artifacts such as gridlines, bad detector rows or columns, horizontal or vertical streaks, or bad pixels. Wire mesh screen images indicated uniform resolution and no geometric distortion.

Mammographic imaging with a small format CCD-based digital cassette: physical characteristics of a clinical system

The physical characteristics of a clinical charge coupled device (CCD)-based imager (Senovision, GE Medical Systems, Milwaukee, WI) for small-field digital mammography have been investigated. The imager employs a MinR 2000 (Eastman Kodak Company, Rochester, NY) scintillator coupled by a 1:1 optical fiber to a front-illuminated 61 x 61 mm CCD operating at a pixel pitch of 30 microns. Objective criteria such as modulation transfer function (MTF), noise power spectrum (NPS), detective quantum efficiency (DQE), and noise equivalent quanta (NEQ) were employed for this evaluation. The results demonstrated a limiting spatial resolution (10% MTF) of 10 cy/mm. The measured DQE of the current prototype utilizing a 28 kVp, Mo-Mo spectrum beam hardened with 4.5 cm Lucite is approximately 40% at close to zero spatial frequency at an exposure of 8.2 mR, and decreases to approximately 28% at a low exposure of 1.1 mR. Detector element nonuniformity and electronic gain variations were not significant after appropriate calibration and software corrections. The response of the imager was linear and did not exhibit signal saturation under tested exposure conditions.

Optimizing parameters for computer-aided diagnosis of microcalcifications at mammography

RATIONALE AND OBJECTIVES

The purpose of this study was to optimize selection of the mammographic features most useful in discriminating benign from malignant clustered microcalcifications.

MATERIALS AND METHODS

The computer-aided diagnosis (CAD) system automatically extracted from digitized mammograms 13 quantitative features characterizing microcalcification clusters. Archival cases (n = 134; patient age range, 31-77 years; mean age, 56.8 years) with known histopathologic results (79 malignant, 55 benign) were selected. Three radiologists at three facilities independently analyzed the microcalcifications by using the CAD system. Stepwise discriminant analysis selected the features best discriminating benign from malignant microcalcifications. A classification scheme was constructed on the basis of these optimized features, and its performance was evaluated by using receiver operating characteristic (ROC) analysis.

RESULTS

Six of the 13 variables extracted by the CAD system were selected by stepwise determinant analysis for generating the classification scheme, which yielded an ROC curve with an area (Az) of 0.98, specificity of 83.64%, positive predictive value of 89.53%, and accuracy of 91.79% for 98% sensitivity. When patient age was an additional variable, the scheme's performance improved, but this was not statistically significant (Az = 0.98). The ROC curve of the classifier (without age as an additional variable) yielded a high Az of 0.96 for patients younger than 50 years and an even higher (P < .02) Az of 0.99 for those 50 years or older.

CONCLUSION

Stepwise discriminant analysis optimized performance of a classification scheme for microcalcifications by selecting six optimized features. Scheme performance was significantly (P < .02) higher for women 50 years or older, but the addition of patient age as a variable did not produce a statistically significant increase in performance.

Full breast digital mammography with an amorphous silicon-based flat panel detector: physical characteristics of a clinical prototype

The physical characteristics of a clinical prototype amorphous silicon-based flat panel imager for full-breast digital mammography have been investigated. The imager employs a thin thallium doped CsI scintillator on an amorphous silicon matrix of detector elements with a pixel pitch of 100 microm. Objective criteria such as modulation transfer function (MTF), noise power spectrum, detective quantum efficiency (DQE), and noise equivalent quanta were employed for this evaluation. The presampling MTF was found to be 0.73, 0.42, and 0.28 at 2, 4, and 5 cycles/mm, respectively. The measured DQE of the current prototype utilizing a 28 kVp, Mo-Mo spectrum beam hardened with 4.5 cm Lucite is approximately 55% at close to zero spatial frequency at an exposure of 32.8 mR, and decreases to approximately 40% at a low exposure of 1.3 mR. Detector element nonuniformity and electronic gain variations were not significant after appropriate calibration and software corrections. The response of the imager was linear and did not exhibit signal saturation under tested exposure conditions.